切换模型

价格榜

MiniMax · MiniMax-M3.1-Flash

各家服务商的价格,从便宜到贵

查看全部模型

价格对比

官方价(现金)
输入 1 / 输出 4 人民币/百万 tokenMiniMax ·
推理服务商最低(现金)
输入 1.05 / 输出 4.2 人民币/百万 tokenTogether AI ·
中转站最低(额度)
未收录

所有美元价格已按 1 美元 = 7 元人民币换算。

全部官方价与推理服务商历史观察

MiniMax · MiniMax-M3.1-Flash 官方价:输入 1、输出 4 人民币/百万 token(MiniMax,2026-11-13 观察)。 推理服务商最低:Together AI 输入 1.05、输出 4.2 人民币/百万 token。 共 73 个站点有可比价格,285 个站点收录了这个模型。

每百万 token 价格区间

官方现金价 · 最低 1.75 · 中位 1.75 · 最高 1.75 · 1 条 人民币 / 每百万 token

推理服务商现金价 · 最低 1.8375 · 中位 1.9294 · 最高 1.9294 · 4 条 人民币 / 每百万 token

每条报价按这个用量混合成一个价:普通输入 75% · 缓存读取 0% · 输出 25% · 缓存写入 0%。只算现在已生效的价。

官方价

服务商计费方式输入输出缓存读取缓存写入单位观察日期条件与来源
MiniMax标准价140.1—人民币 / 1M tokens
原始标价

1.00 / 4.00 CNY / 1M tokens

完整价格条件
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [],
  "effectiveFrom": null,
  "effectiveUntil": null
}

官方来源

所有美元价格已按 1 美元 = 7 元人民币换算。 中转站按公开充值比例估算,分组倍率及金额折扣可能须登录;不代表实付现金资格。

推理服务商

经 OpenRouter 的价,比价和排序用加 5% 费用后的价,原价 × 1.05;原价照列。

服务商计费方式输入输出缓存读取缓存写入经 OpenRouter 加 5% 费用后单位观察日期条件与来源与官方价比较
Together AI标准价1.054.20.105—人民币 / 1M tokens
原始标价

0.15 / 0.60 USD / 1M tokens

完整价格条件
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [],
  "effectiveFrom": null,
  "effectiveUntil": null
}

官方来源
DigitalOcean标准价1.054.20.105—
输入 1.1025
输出 4.41
缓存读取 0.11025
原价 × 1.05
人民币 / 1M tokens
原始标价

0.15 / 0.6 USD / 1M tokens

price listed by OpenRouter for this provider (endpoint digitalocean)
完整价格条件
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.000000015",
    "input": "0.00000015",
    "output": "0.0000006"
  },
  "conditions": [],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "price listed by OpenRouter for this provider (endpoint digitalocean)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

官方来源
Fireworks标准价1.054.20.105—
输入 1.1025
输出 4.41
缓存读取 0.11025
原价 × 1.05
人民币 / 1M tokens
原始标价

0.15 / 0.6 USD / 1M tokens

price listed by OpenRouter for this provider (endpoint fireworks)
完整价格条件
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.000000015",
    "input": "0.00000015",
    "output": "0.0000006"
  },
  "conditions": [],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "price listed by OpenRouter for this provider (endpoint fireworks)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

官方来源
SambaNova标准价1.054.20.105—
输入 1.1025
输出 4.41
缓存读取 0.11025
原价 × 1.05
人民币 / 1M tokens
原始标价

0.15 / 0.6 USD / 1M tokens

price listed by OpenRouter for this provider (endpoint sambanova)
完整价格条件
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.000000015",
    "input": "0.00000015",
    "output": "0.0000006"
  },
  "conditions": [],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "price listed by OpenRouter for this provider (endpoint sambanova)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

官方来源

推理服务商(量化部署)

这些服务商用 fp8、fp4 等低精度部署,价格更低,输出可能和原版有差异。

经 OpenRouter 的价,比价和排序用加 5% 费用后的价,原价 × 1.05;原价照列。

服务商计费方式输入输出缓存读取缓存写入经 OpenRouter 加 5% 费用后单位观察日期条件与来源与官方价比较
StreamLake · fp8 量化标准价0.9453.780.0945—
输入 0.99225
输出 3.969
缓存读取 0.099225
原价 × 1.05
人民币 / 1M tokens
原始标价

0.135 / 0.54 USD / 1M tokens

Quantized deployment (fp8) served through OpenRouter; listed apart from full-precision prices · quantization: fp8 · price listed by OpenRouter for this provider (endpoint streamlake/fp8)
完整价格条件
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.0000000135",
    "input": "0.000000135",
    "output": "0.00000054"
  },
  "conditions": [
    "Quantized deployment (fp8) served through OpenRouter; listed apart from full-precision prices"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "quantization: fp8",
    "price listed by OpenRouter for this provider (endpoint streamlake/fp8)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

官方来源
GMICloud · fp8 量化标准价1.054.20.105—
输入 1.1025
输出 4.41
缓存读取 0.11025
原价 × 1.05
人民币 / 1M tokens
原始标价

0.15 / 0.6 USD / 1M tokens

Quantized deployment (fp8) served through OpenRouter; listed apart from full-precision prices · quantization: fp8 · price listed by OpenRouter for this provider (endpoint gmicloud/fp8)
完整价格条件
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.000000015",
    "input": "0.00000015",
    "output": "0.0000006"
  },
  "conditions": [
    "Quantized deployment (fp8) served through OpenRouter; listed apart from full-precision prices"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "quantization: fp8",
    "price listed by OpenRouter for this provider (endpoint gmicloud/fp8)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

官方来源
InferenceNet · fp4 量化标准价1.054.20.105—
输入 1.1025
输出 4.41
缓存读取 0.11025
原价 × 1.05
人民币 / 1M tokens
原始标价

0.15 / 0.6 USD / 1M tokens

Quantized deployment (fp4) served through OpenRouter; listed apart from full-precision prices · quantization: fp4 · price listed by OpenRouter for this provider (endpoint inference-net/fp4)
完整价格条件
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.000000015",
    "input": "0.00000015",
    "output": "0.0000006"
  },
  "conditions": [
    "Quantized deployment (fp4) served through OpenRouter; listed apart from full-precision prices"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "quantization: fp4",
    "price listed by OpenRouter for this provider (endpoint inference-net/fp4)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

官方来源
InferenceNet · fp4 量化标准价1.054.20.105—
输入 1.1025
输出 4.41
缓存读取 0.11025
原价 × 1.05
人民币 / 1M tokens
原始标价

0.15 / 0.6 USD / 1M tokens

Quantized deployment (fp4) served through OpenRouter; listed apart from full-precision prices · endpoint region: us · quantization: fp4 · price listed by OpenRouter for this provider (endpoint inference-net/fp4/us)
完整价格条件
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.000000015",
    "input": "0.00000015",
    "output": "0.0000006"
  },
  "conditions": [
    "Quantized deployment (fp4) served through OpenRouter; listed apart from full-precision prices"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "endpoint region: us",
    "quantization: fp4",
    "price listed by OpenRouter for this provider (endpoint inference-net/fp4/us)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

官方来源
Nebius · fp4 量化标准价1.054.20.105—
输入 1.1025
输出 4.41
缓存读取 0.11025
原价 × 1.05
人民币 / 1M tokens
原始标价

0.15 / 0.6 USD / 1M tokens

Quantized deployment (fp4) served through OpenRouter; listed apart from full-precision prices · quantization: fp4 · price listed by OpenRouter for this provider (endpoint nebius/fp4)
完整价格条件
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.000000015",
    "input": "0.00000015",
    "output": "0.0000006"
  },
  "conditions": [
    "Quantized deployment (fp4) served through OpenRouter; listed apart from full-precision prices"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "quantization: fp4",
    "price listed by OpenRouter for this provider (endpoint nebius/fp4)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

官方来源
Parasail · fp8 量化标准价1.054.20.105—
输入 1.1025
输出 4.41
缓存读取 0.11025
原价 × 1.05
人民币 / 1M tokens
原始标价

0.15 / 0.6 USD / 1M tokens

Quantized deployment (fp8) served through OpenRouter; listed apart from full-precision prices · quantization: fp8 · price listed by OpenRouter for this provider (endpoint parasail/fp8)
完整价格条件
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.000000015",
    "input": "0.00000015",
    "output": "0.0000006"
  },
  "conditions": [
    "Quantized deployment (fp8) served through OpenRouter; listed apart from full-precision prices"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "quantization: fp8",
    "price listed by OpenRouter for this provider (endpoint parasail/fp8)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

官方来源
其他计费方式与待核报价

官方价

经 OpenRouter 的价,比价和排序用加 5% 费用后的价,原价 × 1.05;原价照列。

服务商计费方式输入输出缓存读取缓存写入经 OpenRouter 加 5% 费用后单位观察日期条件与来源
Minimax标准价1.054.20.105—
输入 1.1025
输出 4.41
缓存读取 0.11025
原价 × 1.05
人民币 / 1M tokens
原始标价

0.15 / 0.6 USD / 1M tokens

OpenRouter endpoint status -2 (not normal) · Served through OpenRouter by the model vendor or a major cloud at its own price (first-tier resale) · price listed by OpenRouter for this provider (endpoint minimax)
完整价格条件
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.000000015",
    "input": "0.00000015",
    "output": "0.0000006"
  },
  "conditions": [
    "OpenRouter endpoint status -2 (not normal)",
    "Served through OpenRouter by the model vendor or a major cloud at its own price (first-tier resale)"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "price listed by OpenRouter for this provider (endpoint minimax)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

官方来源

推理服务商

经 OpenRouter 的价,比价和排序用加 5% 费用后的价,原价 × 1.05;原价照列。

服务商计费方式输入输出缓存读取缓存写入经 OpenRouter 加 5% 费用后单位观察日期条件与来源
OpenRouter · 聚合平台标准价1.054.20.105—
输入 1.1025
输出 4.41
缓存读取 0.11025
原价 × 1.05
人民币 / 1M tokens
原始标价

0.15 / 0.6 USD / 1M tokens

OpenRouter lists time-based price overrides for this model; this is the price outside them
完整价格条件
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.000000015",
    "input": "0.00000015",
    "output": "0.0000006"
  },
  "conditions": [
    "OpenRouter lists time-based price overrides for this model; this is the price outside them"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [],
  "effectiveFrom": null,
  "effectiveUntil": null
}

官方来源
OpenRouter · 聚合平台其他计费方式0.5252.10.0525—
输入 0.55125
输出 2.205
缓存读取 0.055125
原价 × 1.05
人民币 / 1M tokens
原始标价

0.075 / 0.3 USD / 1M tokens

OpenRouter lists time-based price overrides for this model; this is the price outside them · OpenRouter time-based override (UTC): {"utc_end": "100", "utc_start": "1500"}
完整价格条件
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.0000000075",
    "input": "0.000000075",
    "output": "0.0000003"
  },
  "conditions": [
    "OpenRouter lists time-based price overrides for this model; this is the price outside them",
    "OpenRouter time-based override (UTC): {\"utc_end\": \"100\", \"utc_start\": \"1500\"}"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [],
  "effectiveFrom": null,
  "effectiveUntil": null
}

官方来源
OpenRouter · 聚合平台其他计费方式1.054.20.105—
输入 1.1025
输出 4.41
缓存读取 0.11025
原价 × 1.05
人民币 / 1M tokens
原始标价

0.15 / 0.6 USD / 1M tokens

OpenRouter lists time-based price overrides for this model; this is the price outside them · OpenRouter time-based override (UTC): {"utc_end": "1500", "utc_start": "100"}
完整价格条件
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.000000015",
    "input": "0.00000015",
    "output": "0.0000006"
  },
  "conditions": [
    "OpenRouter lists time-based price overrides for this model; this is the price outside them",
    "OpenRouter time-based override (UTC): {\"utc_end\": \"1500\", \"utc_start\": \"100\"}"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [],
  "effectiveFrom": null,
  "effectiveUntil": null
}

官方来源
StreamLake标准价0.9453.780.0945—
输入 0.99225
输出 3.969
缓存读取 0.099225
原价 × 1.05
人民币 / 1M tokens
原始标价

0.135 / 0.54 USD / 1M tokens

Quantized deployment (fp8) served through OpenRouter; listed apart from full-precision prices · quantization: fp8 · price listed by OpenRouter for this provider (endpoint streamlake/fp8)
完整价格条件
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.0000000135",
    "input": "0.000000135",
    "output": "0.00000054"
  },
  "conditions": [
    "Quantized deployment (fp8) served through OpenRouter; listed apart from full-precision prices"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "quantization: fp8",
    "price listed by OpenRouter for this provider (endpoint streamlake/fp8)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

官方来源
InferenceNet标准价1.054.20.105—
输入 1.1025
输出 4.41
缓存读取 0.11025
原价 × 1.05
人民币 / 1M tokens
原始标价

0.15 / 0.6 USD / 1M tokens

Quantized deployment (fp4) served through OpenRouter; listed apart from full-precision prices · quantization: fp4 · price listed by OpenRouter for this provider (endpoint inference-net/fp4)
完整价格条件
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.000000015",
    "input": "0.00000015",
    "output": "0.0000006"
  },
  "conditions": [
    "Quantized deployment (fp4) served through OpenRouter; listed apart from full-precision prices"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "quantization: fp4",
    "price listed by OpenRouter for this provider (endpoint inference-net/fp4)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

官方来源
Nebius标准价1.054.20.105—
输入 1.1025
输出 4.41
缓存读取 0.11025
原价 × 1.05
人民币 / 1M tokens
原始标价

0.15 / 0.6 USD / 1M tokens

Quantized deployment (fp4) served through OpenRouter; listed apart from full-precision prices · quantization: fp4 · price listed by OpenRouter for this provider (endpoint nebius/fp4)
完整价格条件
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.000000015",
    "input": "0.00000015",
    "output": "0.0000006"
  },
  "conditions": [
    "Quantized deployment (fp4) served through OpenRouter; listed apart from full-precision prices"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "quantization: fp4",
    "price listed by OpenRouter for this provider (endpoint nebius/fp4)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

官方来源
Parasail标准价1.054.20.105—
输入 1.1025
输出 4.41
缓存读取 0.11025
原价 × 1.05
人民币 / 1M tokens
原始标价

0.15 / 0.6 USD / 1M tokens

Quantized deployment (fp8) served through OpenRouter; listed apart from full-precision prices · quantization: fp8 · price listed by OpenRouter for this provider (endpoint parasail/fp8)
完整价格条件
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.000000015",
    "input": "0.00000015",
    "output": "0.0000006"
  },
  "conditions": [
    "Quantized deployment (fp8) served through OpenRouter; listed apart from full-precision prices"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "quantization: fp8",
    "price listed by OpenRouter for this provider (endpoint parasail/fp8)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

官方来源
InferenceNet标准价1.054.20.105—
输入 1.1025
输出 4.41
缓存读取 0.11025
原价 × 1.05
人民币 / 1M tokens
原始标价

0.15 / 0.6 USD / 1M tokens

Quantized deployment (fp4) served through OpenRouter; listed apart from full-precision prices · endpoint region: us · quantization: fp4 · price listed by OpenRouter for this provider (endpoint inference-net/fp4/us)
完整价格条件
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.000000015",
    "input": "0.00000015",
    "output": "0.0000006"
  },
  "conditions": [
    "Quantized deployment (fp4) served through OpenRouter; listed apart from full-precision prices"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "endpoint region: us",
    "quantization: fp4",
    "price listed by OpenRouter for this provider (endpoint inference-net/fp4/us)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

官方来源
Together标准价1.054.20.105—
输入 1.1025
输出 4.41
缓存读取 0.11025
原价 × 1.05
人民币 / 1M tokens
原始标价

0.15 / 0.6 USD / 1M tokens

Same provider's price observed directly at www.together.ai; that direct price is listed instead · price listed by OpenRouter for this provider (endpoint together)
完整价格条件
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.000000015",
    "input": "0.00000015",
    "output": "0.0000006"
  },
  "conditions": [
    "Same provider's price observed directly at www.together.ai; that direct price is listed instead"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "price listed by OpenRouter for this provider (endpoint together)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

官方来源
GMICloud标准价1.054.20.105—
输入 1.1025
输出 4.41
缓存读取 0.11025
原价 × 1.05
人民币 / 1M tokens
原始标价

0.15 / 0.6 USD / 1M tokens

Quantized deployment (fp8) served through OpenRouter; listed apart from full-precision prices · quantization: fp8 · price listed by OpenRouter for this provider (endpoint gmicloud/fp8)
完整价格条件
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.000000015",
    "input": "0.00000015",
    "output": "0.0000006"
  },
  "conditions": [
    "Quantized deployment (fp8) served through OpenRouter; listed apart from full-precision prices"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [
    "quantization: fp8",
    "price listed by OpenRouter for this provider (endpoint gmicloud/fp8)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

官方来源
较旧的官方和推理服务商报价

以下为此前收录的报价与当时的条件

推理服务商

经 OpenRouter 的价,比价和排序用加 5% 费用后的价,原价 × 1.05;原价照列。

服务商计费方式输入输出缓存读取缓存写入经 OpenRouter 加 5% 费用后单位观察日期条件与来源
Novita AI标准价1.054.20.105—人民币 / 1M tokens
原始标价

0.15 / 0.6 USD / 1M tokens

完整价格条件
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [],
  "effectiveFrom": null,
  "effectiveUntil": null
}

官方来源
OpenRouter · 聚合平台标准价0.5252.10.0525—
输入 0.55125
输出 2.205
缓存读取 0.055125
原价 × 1.05
人民币 / 1M tokens
原始标价

0.075 / 0.3 USD / 1M tokens

OpenRouter lists time-based price overrides for this model; this is the price outside them
完整价格条件
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "input": "0.000000075",
    "output": "0.0000003",
    "cacheRead": "0.0000000075"
  },
  "conditions": [
    "OpenRouter lists time-based price overrides for this model; this is the price outside them"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [],
  "effectiveFrom": null,
  "effectiveUntil": null
}

官方来源
OpenRouter · 聚合平台标准价1.054.20.105—人民币 / 1M tokens
原始标价

0.15 / 0.6 USD / 1M tokens

OpenRouter lists time-based price overrides for this model; this is the price outside them
完整价格条件
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "input": "0.00000015",
    "output": "0.0000006",
    "cacheRead": "0.000000015"
  },
  "conditions": [
    "OpenRouter lists time-based price overrides for this model; this is the price outside them"
  ],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [],
  "effectiveFrom": null,
  "effectiveUntil": null
}

官方来源
OpenRouter · 聚合平台标准价1.054.20.105—人民币 / 1M tokens
原始标价

0.15 / 0.6 USD / 1M tokens

完整价格条件
{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.000000015",
    "input": "0.00000015",
    "output": "0.0000006"
  },
  "conditions": [],
  "contextTier": null,
  "processingMode": null,
  "conditionNotes": [],
  "effectiveFrom": null,
  "effectiveUntil": null
}

官方来源

所有美元价格已按 1 美元 = 7 元人民币换算。

单位:人民币 / 每百万 Token,按各站标的币种直接比较。

当前显示:特殊分组。这些套餐名里写着测试、内部专用、停用、需要充值或会员等字样,或者倍率接近 0,可能买不到或不稳定。所以单独列出,不参与排名和统计。 返回默认排名

正在按这个服务商筛选:a6api.com

正在搜索…

浏览全部服务商

所有美元价格已按 1 美元 = 7 元人民币换算。

清除筛选

综合价 = 输入价 × 75% + 输出价 × 25%,没算缓存。

价格区间:最低 — · 中位数 — · 最高 —(0 条,人民币/百万总 token)

个站点有可比价格73285 个站点收录了这个模型;按运营方合并约 0 家
最低输入价—人民币 / 1M
各家最低价的中位数—人民币 / 1M

没有可以比较的价格

没有符合筛选条件的价格,可以清除筛选再看。

查看该模型的其他报价与条件
这个榜怎么排的

全站按 Token 计价:共 128,524 条价格,来自 1,383 个网站(约 1,275 家)。其中 109,485 条参与排名,来自 1,349 个网站(约 1,244 家);另有 19,039 条单独列出,不参与排名。价格采集截至 2026-11-15。

这个模型共收录 499 条报价,其中 87 条可以直接比价(84 条参与排名,3 条单独列出)。暂时没法比的原因:还没解析出价格 132 条、倍率疑似没设置 79 条、新价格待审核,暂用上次的价格 19 条、按次或其他单位计价 18 条、显示单位还没确认 6 条。另有 121 条按规则分档计价,在「分档计价」榜里比较

近期报价 0 条,较旧报价 0 条(超过 10 天或这次没更新到)。 这一组没有可以统计的近期报价。

按各站标的币种,统一换算成每百万 Token 的价格;不同币种分开比较。 每一行的输入、输出、缓存价都来自同一个套餐。同一家开的多个网址,在排名里只占一个位置:取其中最便宜的套餐,其他网址列在它下面。判断是不是同一家,依据是报价完全一样、状态页相同或首页代码相同,不代表法律上是同一家公司。想看每个网址的全部价格,可以选「全部套餐」或按服务商筛选。

「自称非官方渠道」是指套餐名里自己写了「逆向」「绕过检测」之类的字样。它们的来源和质量我们没有核实。最低价和中位数只算常规套餐。

完整计价方法 →

常见问题

MiniMax · MiniMax-M3.1-Flash 最便宜的 API 是哪家?

10 天内没有有效报价,较旧的报价列在参考价里。另有 114 条按规则分档的报价,见分档榜。

MiniMax · MiniMax-M3.1-Flash 官方价多少?

输入 1、输出 4 人民币/百万 token,核对于 2026-11-13。 推理服务商最低:Together AI 输入 1.05、输出 4.2 人民币/百万 token。

怎么在 Claude Code 或 Codex 里用 MiniMax · MiniMax-M3.1-Flash?

装 Grandet Skill 后说「帮我把 MiniMax · MiniMax-M3.1-Flash 最便宜的 API 接到 Claude Code」。 安装 Skill →